AI Paper Atlas

Research map / Large language models / Agents, code and math

OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning

Hengrui Kang, Zhuangcheng Gu, Zhiyuan Zhao, Zichen Wen, Bin Wang, Weijia Li, Conghui He

CVPR 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add coarse-grained pretraining on OmniDocLayout-1M before fine adaptation (ablation)OmniDocLayout-LLM 0.5B · M6Doc Newspaper U-CondFID: 42.98 -> 39.73Improved
add coarse-grained pretraining before fine adaptation (ablation)OmniDocLayout-LLM 0.5B · M6Doc Newspaper U-CondOverlap: 8.308 -> 0.084Improved
add coarse-grained pretraining before fine adaptation (ablation)OmniDocLayout-LLM 0.5B · M6Doc Newspaper RefinementFID: 22.07 -> 10.60Improved
add fine-grained adaptation after coarse pretraining (ablation)OmniDocLayout-LLM 0.5B · M6Doc Newspaper U-CondFID: 249.1 -> 39.73Improved
scale model from 0.5B to 3B (ablation)OmniDocLayout-LLM · M6Doc Newspaper C->S+PFID: 10.71 -> 26.88Hurt
scale model from 0.5B to 1.5B (ablation)OmniDocLayout-LLM · M6Doc Newspaper C->S+PFID: 10.71 -> 10.63No clear effect
scale model from 0.5B to 3B (ablation)OmniDocLayout-LLM · M6Doc Newspaper U-CondFID: 39.73 -> 35.81No clear effect
use OmniDocLayout-LLM instead of diffusion-based LayoutDM/LACEdocument layout generation · M6Doc Textbook U-CondFID: 180.25 -> 40.28Improved
use OmniDocLayout-LLM instead of general-purpose LLMs in 0-shotdocument layout generation · M6Doc Newspaper U-CondFID: 171.01 -> 39.73Improved
increase in-context shots for general-purpose LLMsGPT-4o, Gemini-2.5-Flash, Claude-3.7-Sonnet · M6DocFID: GPT-4o textbook U-Cond 135.32 -> 71.56Improved
increase shots beyond 5 for general LLMsgeneral-purpose LLMs · M6Doccost/qualityNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy